VADDPD (ZMM, ZMM, M512) - Port Usage

With blocking instructions for port '0':

• Code:

     0:	41 0f 7e c0          	movd   r8d,mm0
     4:	41 0f 7e c1          	movd   r9d,mm0
     8:	41 0f 7e c2          	movd   r10d,mm0
     c:	41 0f 7e c3          	movd   r11d,mm0
    10:	41 0f 7e c4          	movd   r12d,mm0
    14:	0f 7e c3             	movd   ebx,mm0
    17:	0f 7e c1             	movd   ecx,mm0
    1a:	0f 7e c2             	movd   edx,mm0
    1d:	41 0f 7e c0          	movd   r8d,mm0
    21:	41 0f 7e c1          	movd   r9d,mm0
    25:	62 d1 f5 48 58 06    	vaddpd zmm0,zmm1,ZMMWORD PTR [r14]
  

• Init:

  MOV R15, 10000;
  L: VADDPS ZMM0, ZMM1, ZMM1;
  VADDPS ZMM0, ZMM1, ZMM1;
  DEC R15;
  JNZ L;
  PXOR MM0, MM0;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  VMOVUPD ZMM1, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 11.0
  • Core cycles: 11.09
  • Reference cycles: 6.57
  • UOPS_PORT_0: 10.99

With blocking instructions for port '23':

• Code:

     0:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
     4:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
     8:	45 8b 56 48          	mov    r10d,DWORD PTR [r14+0x48]
     c:	45 8b 5e 4c          	mov    r11d,DWORD PTR [r14+0x4c]
    10:	45 8b 66 50          	mov    r12d,DWORD PTR [r14+0x50]
    14:	41 8b 5e 54          	mov    ebx,DWORD PTR [r14+0x54]
    18:	41 8b 4e 58          	mov    ecx,DWORD PTR [r14+0x58]
    1c:	41 8b 56 5c          	mov    edx,DWORD PTR [r14+0x5c]
    20:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
    24:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
    28:	62 d1 f5 48 58 06    	vaddpd zmm0,zmm1,ZMMWORD PTR [r14]
  

• Init:

  MOV R15, 10000;
  L: VADDPS ZMM0, ZMM1, ZMM1;
  VADDPS ZMM0, ZMM1, ZMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  VMOVUPD ZMM1, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 11.0
  • Core cycles: 5.66
  • Reference cycles: 3.41
  • UOPS_PORT_23: 11.0

With an indexed addressing mode

With blocking instructions for port '0':

• Code:

     0:	41 0f 7e c0          	movd   r8d,mm0
     4:	41 0f 7e c1          	movd   r9d,mm0
     8:	41 0f 7e c2          	movd   r10d,mm0
     c:	41 0f 7e c3          	movd   r11d,mm0
    10:	41 0f 7e c4          	movd   r12d,mm0
    14:	0f 7e c3             	movd   ebx,mm0
    17:	0f 7e c1             	movd   ecx,mm0
    1a:	0f 7e c2             	movd   edx,mm0
    1d:	41 0f 7e c0          	movd   r8d,mm0
    21:	41 0f 7e c1          	movd   r9d,mm0
    25:	62 91 f5 48 58 04 2e 	vaddpd zmm0,zmm1,ZMMWORD PTR [r14+r13*1]
  

• Init:

  MOV R15, 10000;
  L: VADDPS ZMM0, ZMM1, ZMM1;
  VADDPS ZMM0, ZMM1, ZMM1;
  DEC R15;
  JNZ L;
  PXOR MM0, MM0;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  VMOVUPD ZMM1, [R14];
  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 11.0
  • Core cycles: 11.11
  • Reference cycles: 6.57
  • UOPS_PORT_0: 11.0

With blocking instructions for port '23':

• Code:

     0:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
     4:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
     8:	45 8b 56 48          	mov    r10d,DWORD PTR [r14+0x48]
     c:	45 8b 5e 4c          	mov    r11d,DWORD PTR [r14+0x4c]
    10:	45 8b 66 50          	mov    r12d,DWORD PTR [r14+0x50]
    14:	41 8b 5e 54          	mov    ebx,DWORD PTR [r14+0x54]
    18:	41 8b 4e 58          	mov    ecx,DWORD PTR [r14+0x58]
    1c:	41 8b 56 5c          	mov    edx,DWORD PTR [r14+0x5c]
    20:	45 8b 46 40          	mov    r8d,DWORD PTR [r14+0x40]
    24:	45 8b 4e 44          	mov    r9d,DWORD PTR [r14+0x44]
    28:	62 91 f5 48 58 04 2e 	vaddpd zmm0,zmm1,ZMMWORD PTR [r14+r13*1]
  

• Init:

  MOV R15, 10000;
  L: VADDPS ZMM0, ZMM1, ZMM1;
  VADDPS ZMM0, ZMM1, ZMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  VMOVUPD ZMM1, [R14];
  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 11.0
  • Core cycles: 5.66
  • Reference cycles: 3.41
  • UOPS_PORT_23: 11.0